A method and system for storing drug clinical trial data in an anti-counterfeiting manner

Abstract

The present invention relates to the technical field of data security storage, and in particular to an anti-counterfeiting storage method and system for drug clinical trial data, including: obtaining the detection time, subject information and instrument information corresponding to each drug data file during the drug clinical trial process; obtaining file classification coordinates based on the results of classification of different instrument information, combined with subject information and detection time; storing the drug data file using the file classification coordinates to obtain storage address codes; obtaining difference feature codes based on the differences between the drug data file and other drug data files corresponding to the same classification, and the differences between the drug data file and other drug data files corresponding to different classifications; obtaining the hidden key of the corresponding drug data file, combining the private key and public key for encrypting the drug data file, and encrypting and storing the drug data file. The present invention fully guarantees the security of drug clinical trial data by constructing the hidden key of the data file.

Description

Technical Field

[0001] The present invention relates to the technical field of data security storage, and in particular to an anti-counterfeiting storage method and system for drug clinical trial data. Background Art

[0002] The purpose of drug clinical trials is to collect drug-related information in various aspects such as clinical medicine, pharmacology-related effects, adverse reactions and side effects through clinical trials. The drug clinical trial data generated during the drug clinical trial process plays a vital role in drug research and development and the formulation of clinical treatment plans. Therefore, anti-counterfeiting encryption storage methods are currently used when storing drug clinical trial data.

[0003] At present, the commonly used methods for anti-counterfeiting encryption and storage of drug clinical trial data are blockchain technology and digital signature technology. Digital signature technology is based on an asymmetric encryption algorithm. The hash value of the original data is encrypted with a private key to generate a digital signature. The digital signature and the original data file are then sent to the recipient. The recipient decrypts the digital signature with the public key and compares it with the hash value of the obtained data file. If the two are consistent, it means that the data has not been tampered with. However, when the private key is leaked or lost, the digital signature may be forged. When the signature of the document corresponding to the drug clinical trial data needs to be re-verified, the security of the original stored data may not be determined. Summary of the invention

[0004] In order to solve the technical problem that the existing anti-counterfeiting encryption storage method cannot ensure the security of drug clinical trial data when the private key is lost, the purpose of the present invention is to provide an anti-counterfeiting storage method and system for drug clinical trial data. The technical solution adopted is as follows:

[0005] In a first aspect, the present invention provides a method for anti-counterfeiting storage of drug clinical trial data, comprising:

[0006] During the drug clinical trial process, obtain the test time, subject information, and instrument information corresponding to each drug data file when the instrument is used to test the subject;

[0007] Based on the classification results of the similarities between the instrument information corresponding to different drug data files, the file classification coordinates of each drug data file are obtained in combination with each subject information and each detection time; the drug data file is stored using the file classification coordinates to obtain a storage address code;

[0008] According to the data difference between each drug data file and other drug data files corresponding to the same classification in the file classification coordinates, combined with the data difference between each drug data file and other drug data files corresponding to different classifications, a difference feature code for each drug data file is obtained;

[0009] The storage address code and the difference feature code are used to obtain the hidden key of the corresponding drug data file, and the drug data file is encrypted and stored in combination with the private key and the public key for encrypting the drug data file.

[0010] Preferably, the classification result based on the similarity between the instrument information corresponding to different drug data files is combined with each subject information and each detection time to obtain the file classification coordinates of each drug data file, specifically including:

[0011] Based on each subject information corresponding to each drug data file, taking each subject number corresponding to the drug data file as a first dimension coordinate value of the drug data file;

[0012] According to the result of classification between the similarities between the instrument information corresponding to different drug data files, a second dimension coordinate value of each drug data file is obtained, wherein the second dimension coordinate value represents the source information of the corresponding drug data file;

[0013] Determine a time dimension value of each drug data file based on each detection time corresponding to each drug data file;

[0014] The time dimension value, the first dimension coordinate value and the second dimension coordinate value constitute the file classification coordinates.

[0015] Preferably, the result of classifying according to the similarities between the instrument information corresponding to different drug data files to obtain the second dimension coordinate value of each drug data file specifically includes:

[0016] Encoding the instrument information corresponding to each drug data file to obtain the source code of the drug data file, and for any two different drug data files, determining the difference coefficient based on the difference distance between the source codes of the two different drug data files;

[0017] Obtaining a maximum value of the lengths of the source codes of two different drug data files, and determining the source similarity between the two different drug data files based on a negative correlation coefficient of the ratio of the difference coefficient to the maximum value;

[0018] Two different drug data files corresponding to the source similarity being greater than a preset similarity threshold are classified into the same category, and the second dimension coordinate value of each drug data file in each category is obtained according to the classification result of the drug data files.

[0019] Preferably, obtaining the second dimension coordinate value of each drug data file in each category according to the classification result of the drug data file specifically includes:

[0020] The negative correlation coefficient of the total number of drug data files contained in each category is used as the second dimension coordinate value of each drug data file in each category.

[0021] Preferably, the difference feature code of each drug data file is obtained based on the data difference between each drug data file and other drug data files corresponding to the same classification in the file classification coordinates, combined with the data difference between each drug data file and other drug data files corresponding to different classifications, specifically including:

[0022] Any drug data file is taken as the target data file, other drug data files belonging to the same category as the target data file are recorded as reference data files, and other drug data files belonging to different categories from the target data file are recorded as control data files;

[0023] According to the data difference distribution between the target data file and each reference data file, a reference difference feature sequence of the target data file is obtained; according to the data difference distribution between the target data file and each control data file, a control difference feature sequence of the target data file is obtained;

[0024] The data obtained by fusing the reference difference feature sequence and the control difference feature sequence is encoded to obtain the difference feature code of the target data file.

[0025] Preferably, obtaining the reference difference feature sequence of the target data file according to the data difference distribution between the target data file and each reference data file specifically includes:

[0026] Obtain a target information vector of the target data file according to text information and digital information in the target data file, and obtain a reference information vector of the reference data file;

[0027] Determine a difference characteristic factor between the target data file and each reference data file based on a DTW distance between a target information vector of the target data file and a reference information vector of each reference data file;

[0028] When all difference feature factors are less than or equal to a preset difference threshold, the element value in the reference difference feature sequence of the target data file is set to a preset value;

[0029] When at least one of the difference feature factors is greater than a preset difference threshold, the difference information between the target data file and each reference data file corresponding to the difference factor greater than the preset difference threshold is extracted and arranged in sequence to form a reference difference feature sequence of the target data file.

[0030] Preferably, obtaining the target information vector of the target data file according to the text information and digital information in the target data file specifically includes:

[0031] The word vector model is used to process the text information of the target data file to obtain the first feature vector of the target data file, all digital information in the target data file is extracted and normalized, and the second feature vector of the target data file is constructed. The first feature vector and the second feature vector are concatenated to obtain the target information vector of the target data file.

[0032] Preferably, obtaining the control difference feature sequence of the target data file according to the data difference distribution between the target data file and each control data file specifically includes:

[0033] The difference information between the target data file and each control data file is extracted and arranged in sequence to form a control difference feature sequence of the target data file.

[0034] Preferably, the method of obtaining the secret key of the corresponding drug data file by using the storage address code and the difference feature code specifically includes:

[0035] The product of the storage address code and the difference feature code corresponding to each drug data file is used as the secret key of the drug data file.

[0036] In a second aspect, the present invention provides an anti-counterfeiting storage system for drug clinical trial data, the system is used to implement the steps of an anti-counterfeiting storage method for drug clinical trial data, the system comprising:

[0037] The data acquisition module is used to obtain the test time, subject information and instrument information corresponding to each drug data file when the instrument is used to test the subject during the drug clinical trial process;

[0038] The address coding module is used to classify the results according to the similarities between the instrument information corresponding to different drug data files, and combine the information of each subject and each detection time to obtain the file classification coordinates of each drug data file; and use the file classification coordinates to store the drug data file to obtain the storage address code;

[0039] A feature coding module, for obtaining a difference feature coding of each drug data file according to the data difference between each drug data file and other drug data files corresponding to the same classification in the file classification coordinates, combined with the data difference between each drug data file and other drug data files corresponding to different classifications;

[0040] The data storage module is used to obtain the hidden key of the corresponding drug data file by using the storage address code and the difference feature code, and encrypt and store the drug data file in combination with the private key and the public key for encrypting the drug data file.

[0041] The embodiments of the present invention have at least the following beneficial effects:

[0042] The present invention first obtains the detection time, subject information and instrument information corresponding to the drug data file in the clinical trial process, and provides a data basis for the subsequent address analysis of the characteristic distribution of the information data of the three dimensions corresponding to each drug data file. Then, the instrument information of the drug data file is classified, and the source information of the corresponding drug data file is characterized by the instrument information. By analyzing the classification of the drug data file in terms of the source, and combining the information of the two dimensions of time and subject, the file classification coordinates are constructed, which can reflect the relatively unique data inherent attributes of each drug data file, based on which storage and encoding are performed, and the important factors of the first aspect of constructing the hidden key are obtained by analysis. Further, by analyzing the differences between each drug data file and the files in the same category, and the differences between the drug data file and the files in different categories, and performing feature synthesis to determine the encoding corresponding to the unique difference feature information of each drug data file, the important factors of the second aspect of constructing the hidden key are obtained. Finally, considering that the hidden key needs to ensure that the authenticity of the file can be identified after the private key is stolen, the present invention constructs the hidden key of the drug data file based on the unchanged storage address of the drug data file and the unique characteristic information in each drug data file. This can ensure the existence of the original hidden key. Even if the private key is lost and the digital signature is regenerated, the authenticity of the data can be distinguished with the help of the original hidden key, thereby fully ensuring the security of the drug clinical trial data. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1It is a flowchart of the steps of a method for anti-counterfeiting storage of drug clinical trial data provided by the present invention;

[0045] Figure 2 It is a flowchart of the steps of the method for obtaining the file classification coordinates of the drug data file provided by the present invention;

[0046] Figure 3 It is a flowchart of the steps of the method for obtaining the reference difference characteristic sequence provided by the present invention;

[0047] Figure 4 It is a system block diagram of an anti-counterfeiting storage system for drug clinical trial data provided by the present invention;

[0048] Figure 5 The present invention provides a schematic diagram of the structure of a computer device. DETAILED DESCRIPTION

[0049] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the anti-counterfeiting storage method and system for drug clinical trial data proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0050] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0051] The following is a detailed description of a method and system for anti-counterfeiting storage of drug clinical trial data provided by the present invention in conjunction with the accompanying drawings.

[0052] See also Figure 1 , which shows a flowchart of a method for anti-counterfeiting storage of drug clinical trial data provided by an embodiment of the present invention, the method comprising the following steps:

[0053] Step S100, during the drug clinical trial process, obtaining the detection time, subject information and instrument information corresponding to each drug data file when the instrument is used to detect the subject.

[0054] During the clinical trial of a drug, various test data are collected through the hospital's test department, and each drug data file generated when each subject is tested, the test time, subject information, and instrument information corresponding to the drug data file are all recorded to provide a data basis for subsequent data encryption storage.

[0055] It is understandable that each subject will record corresponding identity information when conducting a drug clinical trial, that is, the subject information in this embodiment includes the subject's name, gender, age, previous medical history, allergy history, etc. The subject information can be saved in the form of a subject archive file or a subject medical record file.

[0056] During the clinical trial of a drug, the physiological index data that can be detected by various instruments and equipment is an important part of the drug clinical trial. For example, vital signs data such as blood pressure, heart rate, body temperature, and respiratory rate, which can reflect the impact of the drug on the basic body functions of the subject. At the same time, any symptoms that occur in the subject during the medication process are recorded, including symptoms and adverse reactions related to the expected therapeutic effects of the trial drug. Based on this, in this embodiment, the drug data file can be a comprehensive file containing vital signs data such as blood pressure, heart rate, body temperature, respiratory rate, etc. of the corresponding subject in the corresponding drug clinical trial, as well as symptoms and adverse reaction data of the corresponding subject. In other embodiments, the implementer can select the relevant data of the clinical trial process that needs to be encrypted and stored as the drug data file according to the specific implementation scenario.

[0057] At the same time, in the process of managing clinical trial information, when testing data indicators, the data recording form will not only include the basic information and test results of the subjects, but also record the number of the analyzer used to detect the corresponding indicators. That is, the instrument information in this embodiment includes the corresponding instrument number used when obtaining each drug data file.

[0058] Furthermore, the corresponding time is recorded when each clinical drug test is conducted on each subject, and used as the detection time corresponding to the drug data file obtained from the clinical drug test. In this way, in the subsequent data sorting and analysis process, the data can be conveniently classified and screened according to the instrument number or test time to ensure the quality and reliability of the data.

[0059] Based on this, each drug data file corresponds to a test time, a subject information and an instrument information.

[0060] Step S200, based on the classification results of the similarities between the instrument information corresponding to different drug data files, combined with each subject information and each detection time, obtain the file classification coordinates of each drug data file; use the file classification coordinates to store the drug data file to obtain the storage address code.

[0061] In drug clinical trial data, there are many types of data. In order to better retrieve and organize data, the collected relevant data can be classified according to information such as type or source, and then the drug test data can be stored in different servers or nodes according to the classification results. It can be understood that once the drug data file enters the storage process, as long as the classification of the file content does not undergo an overall and subversive change, the storage address of the corresponding file will not change. Based on this, the encoded information obtained by encoding based on the file storage location is relatively stable and not easily affected by the loss of encrypted data. Therefore, this embodiment considers the first aspect of combining the storage address of the drug data file based on the classification when constructing the hidden key to perform feature analysis.

[0062] First, by performing feature analysis on the collected data, we construct the coordinates where each drug data file can be stored, such as Figure 2 As shown, the method for obtaining the file classification coordinates can be implemented by steps S201 to S204.

[0063] Step S201: Based on the information of each subject corresponding to each drug data file, each subject number corresponding to the drug data file is used as a first dimension coordinate value of the drug data file.

[0064] In this embodiment, each subject is numbered, and then each different subject corresponds to a number. The numbering method can be to number the subjects in the order of the time when the subjects first received the drug clinical trial. The number of the subject corresponding to each drug data file is used as the first dimension coordinate value, that is, the first dimension coordinate value represents the characteristic information of the subject of the drug data file.

[0065] Step S202, obtaining the second dimension coordinate value of each drug data file by classifying the results according to the similarities between the instrument information corresponding to different drug data files.

[0066] The instrument information corresponding to each drug data file reflects the source of the drug data file. By analyzing the similarities and differences in the source information between different drug data files, different categories of drug data files can be identified. Then, data can be stored for drug data files of the same category, and drug data files of different categories can be stored separately. Based on this, the drug data files need to be classified first, and then the corresponding coordinate values ​​need to be determined.

[0067] Specifically, in the first step, the instrument information corresponding to the drug data file needs to be processed so as to classify the instrument information later. Specifically, the instrument information corresponding to each drug data file is encoded to obtain the source code of the drug data file. The encoding method can adopt hash encoding. In other embodiments, the implementer can select according to the specific implementation scenario.

[0068] The second step is to determine the classification measurement parameters based on the differences and similarities of the instrument information between each two different drug data files.

[0069] Specifically, for any two different drug data files, the difference coefficient is determined based on the difference distance between the source codes of the two different drug data files; the maximum value of the length of the source codes of the two different drug data files is obtained, and the source similarity between the two different drug data files is determined based on the negative correlation coefficient of the ratio of the difference coefficient to the maximum value. In this embodiment, the edit distance between the source codes of the two different drug data files is used as the corresponding difference coefficient. In other embodiments, the implementer can select other difference distances for calculation according to the specific implementation scenario.

[0070] As a specific example, the drug data file Drug Data File The source similarity between them can be expressed as: ,in Represents drug data file Drug Data File The source similarity between Represents drug data file Source codes and drug data files The difference distance between the source codes is the difference coefficient; Represents drug data file The length of the source code, Represents drug data file The length of the source code, max() represents the function of finding the maximum value.

[0071] Reflects the drug data file Drug Data File The proportion of the difference information of the corresponding source code. The larger the value, the greater the difference between the two, and the corresponding source similarity The smaller the value of , the more dissimilar the sources of the two may be, which means that the possibility that two different drug data files belong to the same category is smaller.

[0072] The third step is to classify the drug data files based on the corresponding classification measurement parameters between every two different drug data files, namely, source similarity, and then determine the coordinate values ​​of the drug data files in the data source dimension through the classification results.

[0073] Specifically, two different drug data files corresponding to the source similarity greater than a preset similarity threshold are classified into the same category. In this embodiment, the similarity threshold is set to 0.95, and the implementer can set it according to the specific implementation scenario. The source information corresponding to the drug data files contained in each category is relatively close, and it can be roughly regarded that the sources of the drug data files in the same category correspond to the same type.

[0074] Further, the second dimension coordinate value of each drug data file in each category is obtained according to the classification result of the drug data file. Specifically, the negative correlation coefficient of the total number of drug data files contained in each category is used as the second dimension coordinate value of each drug data file in each category, and the second dimension coordinate value represents the source information of the corresponding drug data file.

[0075] In this embodiment, the more the total number of drug data files included in each category, the smaller the value of the second dimension coordinate value of each drug data file in the corresponding category, so the total number of all drug data files included in each category is negatively correlated to obtain the second dimension coordinate value of each drug data file in the corresponding category. The second dimension coordinate value corresponds to the source of each drug data file.

[0076] As a specific example, the reciprocal of the total number of all drug data files contained in each category is used as the second dimension coordinate value of each drug data file in the corresponding category. The implementer can process it according to the specific implementation scenario. At the same time, considering the subsequent use to determine the data storage location, the implementer can also limit the second dimension coordinate value to a positive integer to facilitate the determination of the data storage location, so that the greater the total number of drug data files contained in each category, the smaller the value of the second dimension coordinate value of each drug data file in the corresponding category.

[0077] Step S203: determining the time dimension value of each drug data file based on each detection time corresponding to each drug data file.

[0078] In this embodiment, the detection time corresponding to each drug data file is used as the time dimension value of the drug data file. In other embodiments, the implementer can set it according to the specific implementation scenario. For example, each drug data file is numbered in the order of the detection time corresponding to the drug data file, and the number of the drug data file corresponding to the time is used as the time dimension value of the drug data file. The time dimension value also reflects the time characteristic information of the corresponding drug data file.

[0079] Step S204: the time dimension value, the first dimension coordinate value and the second dimension coordinate value of each drug data file constitute the file classification coordinates.

[0080] The first dimension coordinate value and the second dimension coordinate value of each drug data file constitute the data storage location, and the time dimension value is used as the time storage location corresponding to the separate hierarchical dimension, together constituting the file classification coordinates.

[0081] Furthermore, the file classification coordinates are used to store the drug data files to obtain storage address codes. The data storage location is determined according to the first dimension coordinate value and the second dimension coordinate value of each drug data file, and a two-dimensional network can be formed. Each node in the network corresponds to a hungry storage node, that is, a server, and then each drug data file is stored in a different location according to the hierarchical dimension corresponding to the time dimension. It can be understood that by taking time as a hierarchical dimension, data can be stored separately according to the chronological order, and then a storage structure is constructed according to the two-dimensional data storage location corresponding to each drug data file. This process belongs to the known technology, and only a brief introduction is given here, and no more details are given.

[0082] At this point, each drug data file can obtain a corresponding storage location, and each storage location is encoded using hash coding to obtain the storage address code corresponding to each drug data file. In other embodiments, the implementer can select other appropriate encoding methods according to the specific implementation scenario.

[0083] It should be noted that this embodiment constructs an optimized distributed storage solution. Compared with the existing method of directly storing according to upload time or file type, when storing drug data files, the embodiment of the present invention takes into account the different source types of experimental data, stores different types of files in different servers or hard disks, and can build a more convenient index table. At the same time, when retrieving files, the speed of file search and reading can be greatly improved, and the difficulty of subsequent construction of hidden keys is reduced, providing a certain data foundation.

[0084] Step S300, obtaining the difference feature code of each drug data file according to the data difference between each drug data file and other drug data files of the same classification in the file classification coordinates, combined with the data difference between each drug data file and other drug data files of different classifications.

[0085] In order to ensure the authenticity and security of drug data files when encrypting and storing drug data files, feature codes can be constructed by analyzing feature information of drug data files. When the feature information of drug data files does not change significantly, the corresponding feature codes will not change significantly, thereby ensuring the authenticity and security of data storage. In this embodiment, the data differences of each drug data file in two aspects are analyzed to determine the difference features of each drug data file for encoding. The first aspect analyzes the data differences between drug data files in the same category, and the second aspect analyzes the data differences between drug data files in different categories.

[0086] Specifically, this embodiment takes any drug data file as an example, that is, any drug data file is used as the target data file, other drug data files belonging to the same category as the target data file are recorded as reference data files, and other drug data files belonging to different categories from the target data file are recorded as control data files.

[0087] The first step is to analyze the data differences between the target data file and the drug data files of the same category, that is, to obtain the reference difference feature sequence of the target data file according to the data difference distribution between the target data file and each reference data file. Figure 3 As shown, the method for obtaining the reference difference feature sequence can be implemented by steps S301 to S304.

[0088] Step S301, obtaining a target information vector of a target data file according to text information and digital information in the target data file, and obtaining a reference information vector of a reference data file.

[0089] Specifically, the word vector model is used to process the text information of the target data file to obtain the first feature vector of the target data file, all digital information in the target data file is extracted and normalized, and the second feature vector of the target data file is constructed. The first feature vector and the second feature vector are concatenated to obtain the target information vector of the target data file.

[0090] In this embodiment, the Word2vec bag-of-words model can be used to extract the feature information of the text part in the target data file to form a first feature vector, that is, the first feature vector reflects the text features in the target data file. Further considering that the target data file may also contain digital information, this embodiment directly extracts the digital information and normalizes it to form a second feature vector, and merges the text features and digital features of the target data file in a spliced ​​form to obtain the final target information vector, which is used to characterize the information features contained in the target data file.

[0091] The reference information vector of each reference data file can be obtained in the same way to characterize the information characteristics contained in the reference data file.

[0092] Step S302 : determining a difference characteristic factor between the target data file and each reference data file based on the DTW distance between the target information vector of the target data file and the reference information vector of each reference data file.

[0093] In this embodiment, the normalized value of the DTW distance between the target information vector of the target data file and the reference information vector of each reference data file is used as the difference feature factor between the target data file and each reference data file, which characterizes the feature difference between the target data file and each reference data file. The larger the value of the difference feature factor, the greater the feature difference between the target data file and the reference data file. The smaller the value of the difference feature factor, the smaller the feature difference between the target data file and the reference data file, and the more similar the information between the two is.

[0094] Step S303: when all difference feature factors are less than or equal to a preset difference threshold, the element value in the reference difference feature sequence of the target data file is set to a preset value.

[0095] In this embodiment, the value of the difference threshold is 0.15, and the implementer can set it according to the specific implementation scenario. When the values ​​of the difference feature factors between the target data file and all the reference data files are less than or equal to the difference threshold, it means that the feature information between the target data file and the drug data files in the same category are relatively similar, and the differences are small, which further indicates that there may be no difference feature information in the target data file in the same category, and then it is necessary to perform difference feature analysis on the target data file in different categories. Therefore, this embodiment sets the value of the element in the reference difference feature sequence setting of the target data file at this time to 0, that is, the value of the preset value in this embodiment is 0, and the reference difference feature sequence only contains one element at this time, and the value of the element is 0.

[0096] Step S304, when at least one of the difference feature factors is greater than a preset difference threshold, extract the difference information between the target data file and each reference data file corresponding to the difference factor greater than the preset difference threshold and arrange them in sequence to form a reference difference feature sequence of the target data file.

[0097] For the difference feature factors between the target data file and all the reference data files, when there is at least one factor greater than the difference threshold, it means that at least one drug data file of the same category as the target data file has a difference feature. At this time, the target data file with the difference feature can be compared and analyzed with the reference data file to determine the final reference difference feature sequence.

[0098] More specifically, obtain the reference data file corresponding to the time when the difference feature factor between the target data file and each reference data file is greater than the difference threshold, and record it as the difference data file, compare the difference between the target data file and each difference data file, and extract the information where the difference exists, and arrange the extracted difference information in chronological order of the detection time of the difference data files to form a reference difference feature sequence of the target data file.

[0099] It should be noted that some common text processing tools can be used to compare and extract data from two data files, and the processing method is a well-known technology and will not be introduced in detail here. For example, assuming that the content of file 1 is "Drug A, dosage: 10 mg, expiration date: 2025", and the content of file 2 is "Drug B, dosage: 15 mg, expiration date: 2026", in Python, the difflib module can be used for comparison, and the extracted difference information is file 1: 10 mg and 2025, file 2: 15 mg and 2026. If file 1 is the target data file and file 2 is the reference data file, the reference difference feature sequence composed of the difference information can be expressed as {10 mg, 2025, 15 mg, 2026}.

[0100] Based on this, when arranging the difference information, all feature information contained in the target data file is arranged at the front, and then the difference information corresponding to each reference data file is arranged in chronological order. In other embodiments, the implementer can also set it according to the specific implementation scenario, and it is only necessary to ensure that the reference difference feature sequence can represent the sequence composed of the difference information between the target data file and the drug data file of the same category.

[0101] The second step is to analyze the data differences between the target data file and drug data files in different categories, that is, to obtain the control difference feature sequence of the target data file based on the data difference distribution between the target data file and each control data file.

[0102] It is understandable that each control data file and the target data file do not belong to the same category, that is, there are certain differences between the source information of each control data file and the target data file, which means that there may also be certain differences between the drug clinical trial data between the two. Therefore, the difference characteristics of the test data information between the two can be directly compared.

[0103] At the same time, in this embodiment, the method for obtaining the control difference feature sequence is the same as the method for obtaining the reference difference feature sequence, and only a brief explanation is given here, that is, the difference information between the target data file and each control data file is extracted and arranged in sequence to form the control difference feature sequence of the target data file.

[0104] In the third step, the differential features analyzed from the two aspects are fused and encoded to obtain the encoding corresponding to the differential feature information of each drug data file, providing a data basis for the subsequent acquisition of a hidden key with greater security and stability.

[0105] Specifically, the data after the reference difference feature sequence and the control difference feature sequence are fused is encoded to obtain the difference feature encoding of the target data file. In this embodiment, each drug data file corresponds to a reference difference feature sequence and a control difference feature sequence, which respectively represent two aspects of difference information. It is necessary to perform feature fusion on the difference information of these two aspects, and then perform encoding operation, so as to more comprehensively represent the feature information of each drug data file.

[0106] In this embodiment, the reference difference feature sequence and the control difference feature sequence are spliced ​​to obtain a comprehensive feature sequence, and the elements in the comprehensive feature sequence are encoded to obtain the difference feature encoding of the target data file. The encoding method can be hash encoding, and in other embodiments, other appropriate encoding methods can be selected according to the specific implementation scenario.

[0107] Step S400, using the storage address code and the difference feature code to obtain the hidden key of the corresponding drug data file, combining the private key and the public key for encrypting the drug data file, and encrypting and storing the drug data file.

[0108] The storage address code of each drug data file represents the storage information of the corresponding drug data file classified based on source information, time information and subject information, reflecting the inherent attribute information of the drug data file. The differential feature code of each drug data file represents the data difference feature distribution information between the corresponding drug data file and the drug data files of the same period, and also reflects the unique content of the drug data file. When the feature information represented by the coded data of these two aspects does not change significantly, the corresponding feature code will not change significantly, which can ensure the authenticity and security of data storage.

[0109] Based on this, the encryption key corresponding to each drug data file is adaptively determined by the encoding results in two aspects, so as to ensure the security of the data when the private key is lost. Specifically, the product of the storage address code and the difference feature code corresponding to each drug data file is used as the encryption key of the drug data file.

[0110] An original hidden key is generated when the drug data file is stored for the first time. Thereafter, the digital signature of the data file is generated together with the original hidden key and the private key. The original hidden key, the digital signature and the data file are then stored together in the database. Finally, the decoding key is regenerated during verification, and the digital signature is parsed with the public key. This ensures that the original hidden key remains unchanged no matter how the data is changed. Even if the private key is lost and the digital signature is regenerated, the authenticity of the data can be determined with the help of the original hidden key.

[0111] It should be noted that the user's private key and public key can be obtained according to the encryption algorithm. The specific acquisition method is a well-known technology and will not be introduced in detail here. At the same time, it can be understood that when the drug data file is stored for the first time, it is generally the test data generated after a period of clinical trials, so the stored test data content is fixed.

[0112] like Figure 4 As shown, an embodiment of the present invention further provides an anti-counterfeiting storage system for drug clinical trial data, the system is used to implement the steps of an anti-counterfeiting storage method for drug clinical trial data, the system comprising:

[0113] The data acquisition module is used to obtain the test time, subject information and instrument information corresponding to each drug data file when the instrument is used to test the subject during the drug clinical trial process;

[0114] The address coding module is used to classify the results according to the similarities between the instrument information corresponding to different drug data files, and combine the information of each subject and each detection time to obtain the file classification coordinates of each drug data file; and use the file classification coordinates to store the drug data file to obtain the storage address code;

[0115] A feature coding module, for obtaining a difference feature coding of each drug data file according to the data difference between each drug data file and other drug data files corresponding to the same classification in the file classification coordinates, combined with the data difference between each drug data file and other drug data files corresponding to different classifications;

[0116] The data storage module is used to obtain the hidden key of the corresponding drug data file by using the storage address code and the difference feature code, and encrypt and store the drug data file in combination with the private key and the public key for encrypting the drug data file.

[0117] The present application also provides a computer device. Figure 5 , which shows a schematic diagram of the structure of a computer device provided by an embodiment of the present invention, the computer device includes a memory 501, a processor 502, and a computer program 503 stored in the memory 501 and running on the processor 502, wherein when the processor 502 executes the computer program 503, the computer device can execute any of the anti-counterfeiting storage methods for drug clinical trial data introduced above.

[0118] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer device, the computer device can execute any one of the anti-counterfeiting storage methods for drug clinical trial data introduced above.

[0119] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer device, the computer device can execute any of the anti-counterfeiting storage methods for drug clinical trial data introduced above.

[0120] In the embodiments provided in the present application, it should be understood that the provided computer device, computer program product and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above and will not be repeated here.

[0121] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for anti-counterfeiting storage of drug clinical trial data, characterized in that: The method comprises the following steps: During the drug clinical trial process, obtain the test time, subject information, and instrument information corresponding to each drug data file when the instrument is used to test the subject; According to the classification results of the similarities between the instrument information corresponding to different drug data files, the file classification coordinates of each drug data file are obtained in combination with each subject information and each detection time; the drug data file is stored using the file classification coordinates to obtain a storage address code; According to the data difference between each drug data file and other drug data files corresponding to the same classification in the file classification coordinates, combined with the data difference between each drug data file and other drug data files corresponding to different classifications, a difference feature code for each drug data file is obtained; The hidden key of the corresponding drug data file is obtained by using the storage address code and the difference feature code, and the drug data file is encrypted and stored in combination with the private key and the public key for encrypting the drug data file; When the drug data file is stored for the first time, an original hidden key is generated. Thereafter, the digital signature of the data file is generated with the help of the original hidden key and the private key. The original hidden key, the digital signature and the data file are then stored together in the database. Finally, during verification, a decoding hidden key is regenerated and the digital signature is parsed in combination with the public key. The classification result based on the similarity between the instrument information corresponding to different drug data files is combined with each subject information and each detection time to obtain the file classification coordinates of each drug data file, specifically including: Based on each subject information corresponding to each drug data file, taking each subject number corresponding to the drug data file as a first dimension coordinate value of the drug data file; According to the result of classification between the similarities between the instrument information corresponding to different drug data files, a second dimension coordinate value of each drug data file is obtained, wherein the second dimension coordinate value represents the source information of the corresponding drug data file; Determine a time dimension value of each drug data file based on each detection time corresponding to each drug data file; The time dimension value, the first dimension coordinate value and the second dimension coordinate value constitute the file classification coordinates.

2. The anti-counterfeiting storage method for drug clinical trial data according to claim 1, characterized in that: The result of classifying according to the similarities between the instrument information corresponding to different drug data files, obtaining the second dimension coordinate value of each drug data file, specifically includes: Encoding the instrument information corresponding to each drug data file to obtain the source code of the drug data file, and for any two different drug data files, determining the difference coefficient based on the difference distance between the source codes of the two different drug data files; Obtaining a maximum value of the lengths of the source codes of two different drug data files, and determining the source similarity between the two different drug data files based on a negative correlation coefficient of the ratio of the difference coefficient to the maximum value; Two different drug data files corresponding to the source similarity being greater than a preset similarity threshold are classified into the same category, and the second dimension coordinate value of each drug data file in each category is obtained according to the classification result of the drug data files.

3. The anti-counterfeiting storage method for drug clinical trial data according to claim 2, characterized in that: The step of obtaining the second dimension coordinate value of each drug data file in each category according to the classification result of the drug data file specifically includes: The negative correlation coefficient of the total number of drug data files contained in each category is used as the second dimension coordinate value of each drug data file in each category.

4. The anti-counterfeiting storage method for drug clinical trial data according to claim 1, characterized in that: The difference feature code of each drug data file is obtained based on the data difference between each drug data file and other drug data files corresponding to the same classification in the file classification coordinates, combined with the data difference between each drug data file and other drug data files corresponding to different classifications, specifically including: Any drug data file is taken as the target data file, other drug data files belonging to the same category as the target data file are recorded as reference data files, and other drug data files belonging to different categories from the target data file are recorded as control data files; According to the data difference distribution between the target data file and each reference data file, a reference difference feature sequence of the target data file is obtained; according to the data difference distribution between the target data file and each control data file, a control difference feature sequence of the target data file is obtained; The data obtained by fusing the reference difference feature sequence and the control difference feature sequence is encoded to obtain the difference feature code of the target data file.

5. The anti-counterfeiting storage method for drug clinical trial data according to claim 4, characterized in that: The step of obtaining a reference difference feature sequence of the target data file according to the data difference distribution between the target data file and each reference data file specifically includes: Obtain a target information vector of the target data file according to text information and digital information in the target data file, and obtain a reference information vector of the reference data file; Determine a difference characteristic factor between the target data file and each reference data file based on a DTW distance between a target information vector of the target data file and a reference information vector of each reference data file; When all difference feature factors are less than or equal to a preset difference threshold, the element value in the reference difference feature sequence of the target data file is set to a preset value; When at least one of the difference characteristic factors is greater than a preset difference threshold, the difference information between the target data file and each reference data file corresponding to the difference factor greater than the preset difference threshold is extracted and arranged in sequence to form a reference difference characteristic sequence of the target data file.

6. The anti-counterfeiting storage method for drug clinical trial data according to claim 5, characterized in that: The step of obtaining the target information vector of the target data file according to the text information and digital information in the target data file specifically includes: The word vector model is used to process the text information of the target data file to obtain the first feature vector of the target data file, all digital information in the target data file is extracted and normalized, and the second feature vector of the target data file is constructed. The first feature vector and the second feature vector are concatenated to obtain the target information vector of the target data file.

7. The anti-counterfeiting storage method for drug clinical trial data according to claim 6, characterized in that: The step of obtaining the control difference feature sequence of the target data file according to the data difference distribution between the target data file and each control data file specifically includes: The difference information between the target data file and each control data file is extracted and arranged in sequence to form a control difference feature sequence of the target data file.

8. The anti-counterfeiting storage method for drug clinical trial data according to claim 1, characterized in that: The method of obtaining the secret key of the corresponding drug data file by using the storage address code and the difference feature code specifically includes: The product of the storage address code and the difference feature code corresponding to each drug data file is used as the secret key of the drug data file. 9.An anti-counterfeiting storage system for drug clinical trial data, characterized in that: The system is used to implement the steps of a method for anti-counterfeiting storage of drug clinical trial data as described in any one of claims 1 to 8, and the system comprises: The data acquisition module is used to obtain the test time, subject information and instrument information corresponding to each drug data file when the instrument is used to test the subject during the drug clinical trial process; The address coding module is used to classify the results according to the similarities between the instrument information corresponding to different drug data files, and combine the information of each subject and each detection time to obtain the file classification coordinates of each drug data file; and use the file classification coordinates to store the drug data file to obtain the storage address code; A feature coding module, for obtaining a difference feature coding of each drug data file according to the data difference between each drug data file and other drug data files corresponding to the same classification in the file classification coordinates, combined with the data difference between each drug data file and other drug data files corresponding to different classifications; The data storage module is used to obtain the hidden key of the corresponding drug data file by using the storage address code and the difference feature code, and encrypt and store the drug data file in combination with the private key and the public key for encrypting the drug data file.

Images